Cities are the centres of communication, commerce, and culture. Although, more than 80% of global GDP is generated in urban districts, the cities consume two-thirds of global resources and produce more than 70% of global CO2 emissions. Rising population, escalating urban pollution, the effects of climate change urge cities to search for innovative solutions that will help mitigating rising urban problems, safeguarding more liveable future for its citizens. Among most pending issues, air pollution and heat stress have been highlighted by significant amount of the scientific research. In the Netherlands, air pollution shortens societal life expectancy by 13 months. Heat stress, on the other side is responsible for the increase in societal morality by 12% during the heat waves. The effects of climate change are predicted to bring more heatwaves in the future creating a significant risk to the vulnerable groups of the society. Recent technological development that embraces more feasible sensing technology, increasing connectivity and advanced computing platforms, creates a vast opportunity to design solutions that will help to map the hotspots of less obvious data like air pollution or heat stress.
This report proposes a monitoring solution that helps thoroughly gather, analyse, and report the data which can be used by the policymakers while designing solutions for urban areas. The solution was defined basing on a set of reference studies that display example practice for air quality and temperature monitoring. The reference studies represent four different monitoring initiatives. In Chicago program called Array of Things is being implemented; Barcelona’s smart initiative is called Sentilo; Copenhagen deploys smart solutions through Copenhagen Connecting; Singapore has its Smart Nation Sensor Platform. The reference studies served as an input for identifying a framework that consist of 8 enablers for smart initiative deployment. Further, technology and data analysis and display enablers were explored in detail. The solution composes of four stages namely: Physical infrastructure, cloud, data analysis platform, visualisation, and information hubs. The physical infrastructure includes selection of sensing technology that closely monitors air quality and heat through fixed, mobile, and participatory sensors. The cloud stores and computes data received and sends it to data analysis platform where four engines further analyse and report data to information hubs. City managers and third party can access the information through an application that displays real-time information about air quality and heat, being able to send alerts or predict the most optimal route throughout the city. Further, the information gathered can be envisioned in real time in a 3D model of a city – a Digital Twin. There are other factors that are deemed to be important like partnerships and funding and they are stated in the model, but they were not the focal points of the research and are included in the recommendation section.

Understanding energy consumption behavior provide an insightful knowledge to improve energy efficiency, promote energy conservation, and importantly sustain the human life. However, currently energy consumption data are being gathered by (smart) energy meters at the household level or through surveys. While gathering data using smart meter is highly reliable, it lacks semantic information about how energy is consumed (e.g. using appliance). On the other hand, survey allow to gather semantically rich data, but the acquisition of the data is labor-intensive. In this context, social media data data (e.g. twitter, instagram) which are semantically rich and publicly available can be used as an alternative source of data about energy consumption behavior. However, due to the noisy and ambiguous nature of social media data, the extraction of energy related information from micro posts is very challenging. The aim of this thesis is to introduce a general framework to discover knowledge about energy consumption behaviors from social media data. The framework explores the suitable of social media data as an alternative data source for capturing energy consumption behaviors, and thus to be used to complement conventional data sources. Using the state-of-the-art methods and approaches in social media data analytics field, we compose the framework which structured into three main stages: data collection, data enrichment & processing, and data analysis & visualization. To study the performance of our framework, we set up an experiment aiming at identifying energy consumption behavior patterns in two different world cities: Jakarta (Indonesia) and Amsterdam (The Netherlands). On data collection stage, we collected 1,306,336 tweets from both cities. Next, on data enrichment & processing stage, we pre-processed the collected tweets and conduct dictionary-based annotation using our 8,329 energy consumption related terms. As a result, we identified 509,471 tweets (39%) of the corpus as energy consumption related tweets, which categorize into four different energy consumption behaviors: food, dwelling, mobility and leisure. Using the annotated streams as noisy datasets, we implement distant supervision machine learning technique using binomial classifier to identify energy consumption related tweets. Following this approach, we are able to achieve good classifier’s performance on identifying energy consumption related tweets. Finally, on data analysis & visualization stage, we conduct statistical analysis and found strong positive correlation (r = 0.73) between energy consumption data extracted from social media and actual electricity load. Following this result, we show that social media data has the potential to be used as supplementary source of information for energy consumption studies.